kostiantynk1205 commited on
Commit
e933598
·
verified ·
1 Parent(s): 9137d4b

Training in progress, step 6, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1d9f92c927edd91a49d167a36f6b288492dda621f6236d3069baf2f2ae895331
3
  size 125248064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93cd3bce8c727a6160a02caca85a00ea7253b29c35a7c02d59a92da022007b92
3
  size 125248064
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cbd3765e2a67947c32830e47269a1a04014fb88bbac3b79f1a4e31eda5676877
3
  size 64219860
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4c8a0b2c32ed9365ab057e8d0b35c651ed28260e86a77c62b3f6a564efa7f29
3
  size 64219860
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9cf86cd5b19b8056a2759fc36b0c4f0323fb9c04403c19df65bcd5311b20dea5
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:693d65ff7d3abbbb13c7ee57d38fa6e7fa5181ebaaabad321dd22b54929bbad4
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.013969732246798603,
5
  "eval_steps": 3,
6
- "global_step": 3,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -44,6 +44,35 @@
44
  "eval_samples_per_second": 20.158,
45
  "eval_steps_per_second": 10.19,
46
  "step": 3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47
  }
48
  ],
49
  "logging_steps": 1,
@@ -63,7 +92,7 @@
63
  "attributes": {}
64
  }
65
  },
66
- "total_flos": 949861629296640.0,
67
  "train_batch_size": 2,
68
  "trial_name": null,
69
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.027939464493597205,
5
  "eval_steps": 3,
6
+ "global_step": 6,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
44
  "eval_samples_per_second": 20.158,
45
  "eval_steps_per_second": 10.19,
46
  "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.018626309662398137,
50
+ "grad_norm": 0.9486850500106812,
51
+ "learning_rate": 8e-05,
52
+ "loss": 1.982,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.023282887077997673,
57
+ "grad_norm": 1.1441988945007324,
58
+ "learning_rate": 0.0001,
59
+ "loss": 2.0982,
60
+ "step": 5
61
+ },
62
+ {
63
+ "epoch": 0.027939464493597205,
64
+ "grad_norm": 1.3133906126022339,
65
+ "learning_rate": 0.00012,
66
+ "loss": 2.1796,
67
+ "step": 6
68
+ },
69
+ {
70
+ "epoch": 0.027939464493597205,
71
+ "eval_loss": 2.165942907333374,
72
+ "eval_runtime": 4.5309,
73
+ "eval_samples_per_second": 20.084,
74
+ "eval_steps_per_second": 10.152,
75
+ "step": 6
76
  }
77
  ],
78
  "logging_steps": 1,
 
92
  "attributes": {}
93
  }
94
  },
95
+ "total_flos": 1899723258593280.0,
96
  "train_batch_size": 2,
97
  "trial_name": null,
98
  "trial_params": null